Triple
T34976067
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Krakozhian |
E1008679
|
entity |
| Predicate | usedForWrittenTextInWork |
P169228
|
FINISHED |
| Object | news headlines |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: news headlines | Statement: [Krakozhian, usedForWrittenTextInWork, news headlines]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedForWrittenTextInWork Context triple: [Krakozhian, usedForWrittenTextInWork, news headlines]
-
A.
usedInWriting
Indicates that something (such as a tool, material, or medium) is employed as part of the process or act of writing.
-
B.
usedInWritingFor
chosen
Indicates that something (e.g., a tool, material, or medium) is employed as part of the process or context of writing for a particular purpose or audience.
-
C.
usesWritingsOf
Indicates that one entity makes use of, relies on, or draws from the writings or written works produced by another entity.
-
D.
writtenForWork
Indicates that something was created or authored specifically as part of, or in fulfillment of, a work-related task or professional duty.
-
E.
textWrittenFor
Indicates that a piece of text was created with a particular intended audience, purpose, or recipient in mind.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69f76dc78a308190a1ac29ad4a9a4895 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fd2839880c819099a7a89783f2270e |
completed | May 8, 2026, 12:03 a.m. |
| PD | Predicate disambiguation | batch_69fd23dc5da48190ae8ba08947d34956 |
completed | May 7, 2026, 11:44 p.m. |
Created at: May 3, 2026, 4:01 p.m.